Multiverse: Language-Conditioned Multi-Game Level Blending via Shared Representation

TL;DR

Multiverse is a multi-game level generator that uses shared representations and contrastive learning to enable cross-game blending guided by natural language descriptions.

Contribution

It introduces a shared latent space and contrastive supervision for language-conditioned multi-game level blending and zero-shot generation.

Findings

Supports controllable cross-game level blending.

Improves blending quality within the same genre.

Enables zero-shot generation from textual prompts.

Abstract

Text-to-level generation aims to translate natural language descriptions into structured game levels, enabling intuitive control over procedural content generation. While prior text-to-level generators are typically limited to a single game domain, extending language-conditioned generation to multiple games requires learning representations that capture structural relationships across domains. We propose Multiverse, a language-conditioned multi-game level generator that enables cross-game level blending through textual specifications. The model learns a shared latent space aligning textual instructions and level structures, while a threshold-based multi-positive contrastive supervision links semantically related levels across games. This representation allows language to guide which structural characteristics should be preserved when combining content from different games, enabling controllable blending through latent interpolation and zero-shot generation from compositional textual prompts. Experiments show that the learned representation supports controllable cross-game level blending and significantly improves blending quality within the same game genre, while providing a unified representation for language-conditioned multi-game content generation.